Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to running activities or movements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "run" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hots
    -0.72
     Aires
    -0.65
     defe
    -0.61
    alam
    -0.60
     defic
    -0.60
     suscept
    -0.59
     Emer
    -0.59
    oshop
    -0.58
    theless
    -0.57
    ĵĺ
    -0.57
    POSITIVE LOGITS
    aways
    1.24
    swick
    1.20
    gs
    1.19
    nings
    1.10
    ners
    1.10
    escape
    1.07
    ways
    1.04
    nell
    1.00
    away
    0.98
    estones
    0.97
    Act Density 0.054%

    No Known Activations